BUSOBA 2320: Review Midterm 2 (Flow Chart)

FLOW CHART

0

Thought Process PT 1

• 1 Type of Data

• 2 Parameter and Statistic

Thought Process PT 2

• 3 Number of Groups

• 4 Additional Conditions

Thought Process PT 3

• 5 Model

• 6 Common Name

Attribute

Google AI: Qualitative. Based on characteristics or categories.

Variable

Google AI: Quantitative.

One Proportion Z

Attribute Data, Proportion, One Sample, Z, _

Two Proportion Z

Attribute Data, Proportion, Two Samples, Z, _

Chi Square Test / x²

Attribute Data, Proportion, More than 2 Samples, x², _

STOP

Variable Data, Variance, _

For variable data, we are just dealing with

mean. Not variance.

One Sample Z

Variable Data, Mean, One Sample, Pop Stan Dev ² is KNOWN, Z, _

One Sample T

Variable Data, Mean, One Sample, Pop Stan Dev ² is UNKNOWN, t(n-1), _

Two Sample Z

Variable Data, Mean, Two Samples, INDPENDENT Samples, BOTH Pop Stan Dev ² is KNOWN, Z, _

Two Sample T POOLED Variance

Variable Data, Mean, Two Samples, INDPENDENT Samples, BOTH Pop Stan Dev ² are UNKNOWN, EQUAL Variances, t(n1 + n2 - 2), _

Two Sample T SEPARATE Variances

Variable Data, Mean, Two Samples, INDPENDENT Samples, BOTH Pop Stan Dev ² are UNKNOWN, UNEQUAL Variances, t(Satterthwaite), _

Paired (Matched) Samples T

Variable Data, Mean, Two Samples, Paired Samples, Pop Stan Dev Differences ² UNKNOWN, t(nd - 1), _

ANOVA

Variable Data, Mean, MORE THAN 2 Samples, Equal Population Variances, F(df treatment, df error), _

APPROPRIATE ANALYSIS METHOD

0

Quantitative or continuous: Variable

data that is the result of measuring: Time, volume, distance,

etc.

Qualitative or Categorical: Attribute

binary (yes/no, 0/1, etc.), ordinal (good/better/best, etc.), nominal

(Gender, Day of Week, Brand of cell phone, etc.)

Event count, like number of defects, is

technically discrete (categorical) but is often

treated as quantitative (VARIABLE)

To determine what analysis type to use PT 1

– Determine your response variable, Y

– Determine if your response variable is quantitative or categorical

To determine what analysis type to use PT 2

- What is(are) your input(s)?

– Is your input quantitative or categorical

Comparing one response to a constant

One-sample t-test for a

quantitative Y

Comparing one response to a constant

One proportion test for a

categorical Y

Comparing two responses to one another

Two-sample t-test for a

quantitative Y

Comparing two responses to one another

Two Proportions test for a

categorical Y

Comparing more than two means/levels

– ANOVA

Comparing more than two proportions

– Chi Sq

HYPOTHESIS

0

Comparison/ Two Sample Ex.

Ho: μ1 – μ2 = 0

Ha: μ1 – μ2 ≠ 0

Comparison/ Two Sample Ex. MORE Ha:

μ1 – μ2 ≠ 0

Comparison/ Two Sample Ex. 2

Ho: p1 – p2 = 0

Ha: p1 – p2 ≠ 0

Chi Square/Test of Independence

H0: “Variable A” and “Variable B” are independent of (or NOT associated with) each other

HA: “Variable A” and “Variable B” are NOT independent of (or are associated with) each other

Chi Square/Test of Independence MORE Ha: are

NOT independent of (or are associated with) each other

Chi Square/Test of Homogeneity

H0: The probabilities of the different categories occurring is the same in all populations being compared.

HA: The probabilities of the different categories occurring is NOT the same in all populations being compared.

Chi Square/Test of Homogeneity MORE Ha: is

NOT the same in all populations being compared.

Chi Square/ Test of Goodness-of-Fit

H0: “Variable of interest” is accurately modeled with “description of distribution”

HA: “Variable of interest” is not accurately modeled with “description of distribution”

Chi Square/ Test of Goodness-of-Fit MORE Ha: is

not accurately modeled with “description of distribution”

ANOVA

H0: μ1 = μ2 = … = μk

Ha: Not all μi are the same, or HA: At least two μi are different

ANOVA MORE Ha:

Not all μi are the same, or HA: At least two μi are different